Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/zebbern/claude-code-guide/html-injection-testingnpx skills add zebbern/claude-code-guide --skill html-injection-testinggit clone --depth 1 https://github.com/zebbern/claude-code-guideWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00058 | $0.03443 |
| Opus 5 | $0.00029 | $0.01722 |
| Sonnet 5 | $0.00012 | $0.00689 |
| Haiku 4.5 | $0.00006 | $0.00344 |
Grade A, and why
html-injection-testing scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -X POST -d "comment=<div style='color:red'>Malicious Content</div>" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl "http://target.com/search?q=<h1>Test</h1>" How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Injection Testing
Purpose
Identify and exploit HTML injection vulnerabilities that allow attackers to inject malicious HTML content into web applications. This vulnerability enables attackers to modify page appearance, create phishing pages, and steal user credentials through injected forms.
Prerequisites
Required Tools
- Web browser with developer tools
- Burp Suite or OWASP ZAP
- Tamper Data or similar proxy
- cURL for testing payloads
Required Knowledge
- HTML fundamentals
- HTTP request/response structure
- Web application input handling
- Difference between HTML injection and XSS
Outputs and Deliverables
- Vulnerability Report - Identified injection points
- Exploitation Proof - Demonstrated content manipulation
- Impact Assessment - Potential phishing and defacement risks
- Remediation Guidance - Input validation recommendations
Core Workflow
Phase 1: Understanding HTML Injection
HTML injection occurs when user input is reflected in web pages without proper sanitization:
<!-- Vulnerable code example -->
<div>
Welcome, <?php echo $_GET['name']; ?>
</div>
<!-- Attack input -->
?name=<h1>Injected Content</h1>
<!-- Rendered output -->
<div>
Welcome, <h1>Injected Content</h1>
</div>
Key differences from XSS:
- HTML injection: Only HTML tags are rendered
- XSS: JavaScript code is executed
- HTML injection is often stepping stone to XSS
Attack goals:
- Modify website appearance (defacement)
- Create fake login forms (phishing)
- Inject malicious links
- Display misleading content
Phase 2: Identifying Injection Points
Map application for potential injection surfaces:
1. Search bars and search results
2. Comment sections
3. User profile fields
4. Contact forms and feedback
5. Registration forms
6. URL parameters reflected on page
7. Error messages
8. Page titles and headers
9. Hidden form fields
10. Cookie values reflected on page
Common vulnerable parameters:
?name=
?user=
?search=
?query=
?message=
?title=
?content=
?redirect=
?url=
?page=
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 499 lines · 58 tokens per session scan A 0698b5b945b4
html-injection-testing is a skill published in the GitHub repository zebbern/claude-code-guide (4,596 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 3,443 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cdb-scan
Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…
mckinsey-consultant
McKinsey顾问式问题解决系统。从商业问题出发,通过假设驱动的结构化分析方法,生成McKinsey风格研究报告和PPT。融合Problem Solving方法论、MECE原则、Issue Tree拆解、Hypotheses形成、Dummy Page设计、智能数据收集和专业PPT生成能力。.
exam-coach
Quiz and coach the user for the Anthropic Claude certification exams using this repository's blueprints and official exam guides. Use when the user asks to practice, be quizzed, drill a domain, take a mock exam, or prepare for the Associate, Developer, or Architect certifications.
security-claude
Skill "security-claude" from rahozosman/security-claude, covering security architecture & threat modeling intelligence, how this skill is organized (progressive disclosure), 1. pick a mode, 2. core method (applies to every mode) and 3. doing a focused review.
bridger
Coordinate with another Claude Code session over the bridge — discover peers, ask them, answer their questions — INSTEAD of guessing or asking the user. Trigger this the moment the task depends on something another repo's session knows: a dependency/library that changed and this code consumes it, an API or schema…
run-tests
Run the pytest suite, report pass/fail counts and coverage, and identify untested code. Use when the user asks to run tests, check test coverage, or verify that changes didn't break anything.